Please wait ...
0% Complete
Home
/
14th International Conference on Computer and Knowledge Engineering
Non-Negative Matrix Factorization improves Residual Neural Networks
Authors :
Hojjat Moayed
1
1- Esfarayen University of Technology
Keywords :
ResNet،Residual Neural Network،NMF،Deep Learning
Abstract :
Residual neural networks enable the use of very deep architectures. These architectures benefit by passing the identity information from a layer directly to subsequent layers. Extensive research has been conducted to improve the performance of residual neural networks. In this paper, we propose a method to improve performance by providing a more informative input using non-negative matrix factorization. The method combines the invariant features learned from the training data with the extracted, fine-tuned features at the end of the residual block. Our experimental results confirm that the proposed architecture improves performance on the image classification task.
Papers List
List of archived papers
Adversarial Robustness Evaluation with Separation Index
Bahareh Kaviani Baghbaderani - Afsaneh Hasanebrahimi - Ahmad Kalhor - Reshad Hosseini
A Comprehensive Dataset of Real-scene Images for Text Detection and Recognition in Persian
Iman Souzanchi - Ramin Rahimi - Mohammad Ali Majidi Anvari - Atefeh Baniasadi - Ashkan Sadeghi - Mohammad Reza Mohammadi
Depression Diagnosis Using Optimization of Nonlinear EEG Features Based on Parametric Learning Tactics
Ali Asadi Zeidabadi - Melika Changizi - Mahdi Zolfagharzadeh Kermani - Sara Bargi Barkouk
Segmentation of Hard Exudates in Retinal Fundus Images Using BCDU-Net
Nafise Ameri - Nasser Shoeibi - Mojtaba Abrishami
SUBoost: A Novel Boosting-Based Selective Undersampling for handling Imbalanced Data
Nima Rasi Baghmishe - Jafar Tanha - Ehsan Roshan
Adaptive Pattern Reconstruction Using Linear Regression for Improved TPS Anomaly Detection
Ali Azarsina - Alireza Safarzadeh - MohammadReza Jamali - Abdolhossein Vahabie
The application of Brain Drain Optimization algorithm on static drone placement problem
Mohammad Mehdi Samimi - Alireza Basiri
A novel hybrid DMHS-GMDH algorithm to predict COVID-19 pandemic time series
Ahmad Taheri - Shahriar Ghashghaei - Amin Beheshti - Keyvan RahimiZadeh
Detecting Non-Spherical Clusters Using Modified CURE Algorithm
Arezou Safdari - Pedram Salehpour
An overview of Business Intelligence research in healthcare organizations using a topic modeling approach
Mohammad Mehraeen - Laya Mahmoudi - Mohammad Hossein Sharifi
more
Samin Hamayesh - Version 46.0.2